© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49290
    Prev
    Next
    INDEX
    Explanations

    timed animation delays

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on code import paths or identifiers containing “scroll‐reveal,” i.e. it spots the “scroll‐reveal” library reference.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naer
    -1.02
     oogen
    -0.98
     fara
    -0.97
     excur
    -0.96
     resolu
    -0.94
     bont
    -0.89
     hie
    -0.88
     eene
    -0.88
     quitt
    -0.88
     maten
    -0.87
    POSITIVE LOGITS
     delay
    1.71
    delay
    1.46
    Delay
    1.39
     Delay
    1.34
     delaying
    1.30
     delayed
    1.27
     delays
    1.23
     sequentially
    1.09
    DELAY
    1.09
    延迟
    1.03
    Activations Density 0.017%

    No Known Activations